CHATBOTS

Slack Facilities Request Triage Bot

Captures facilities complaints posted in a Slack channel, classifies the issue type and urgency, logs a tracked ticket in Airtable, and confirms back with a ticket number.

CategoryChatbots
Enginepaperclip
Difficultybeginner
Triggerevent
Steps5
Setup~5 min

How it runs

The automated pipeline, trigger to output.

  • TriggerMessage posted in the #facilities Slack channelSlack
  • ActionClassify issue category and urgencyOpenAI
  • ActionCreate a tracked ticket row in AirtableAirtableAirtable
  • LogicFlag high-urgency tickets for escalation
  • OutputReply in Slack thread with the ticket IDSlack

What it does

Turns ad-hoc facilities gripes ("the AC in room 3 is broken", "out of coffee in the kitchen") into structured, tracked tickets. The bot reads each request, categorizes it, records it in an Airtable tracker, and replies with a reference number so the requester knows it's logged.

When to use it

Use this when facilities or office-ops requests come in scattered across Slack and nothing gets tracked. It gives the office manager a single Airtable queue with category, urgency, and status, while employees keep using the channel they already know.

How it works

  1. 1A message is posted in the designated #facilities Slack channel.
  2. 2The agent classifies the request into a category (HVAC, supplies, cleaning, electrical, other) and assigns an urgency level.
  3. 3A new row is created in the Airtable facilities tracker with the description, category, urgency, requester, and an Open status.
  4. 4The bot reacts to the original message and replies in-thread with the generated ticket ID and expected handling.
  5. 5High-urgency tickets are flagged so the office manager can spot them at a glance.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect SlackChannels, DMs, threads, mentions.
  2. 2
    Connect AirtableBases, tables, views, automations.
  3. 3
    Connect OpenAIModels, embeddings, files.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.